Tools as code
ElevenAgents tools can now be built in code with the tool builder in the Python and JavaScript SDKs, from v2.79.0. Define webhook, client and system tools with chained calls such as get(), header() and assign(), then pass the result of build() to tools.create() or tools.update(). The builder keeps path parameters, required lists and value sources consistent, runs entirely in the SDK, and produces tools you can still edit in the dashboard. See Tools as code.
Lower Speech to Text prices
Speech to Text now costs $0.20 per hour of audio for batch transcription and $0.22 per hour for realtime transcription, for every Scribe model on all self-serve and Business plans. Enterprise pricing is unchanged. See Speech to Text for the available models.
Content Provenance API
Content provenance has a beta endpoint, POST /v1/content-provenance/watermark, that checks an uploaded audio file for an ElevenLabs watermark. It returns is_detected and, when the generation can be identified, the product, model, generated_at time and unique_id of the generation, never the prompt or the account behind it. API keys need the new watermark permission. See Content provenance.
Build and publish agents from the hosted MCP
Hosted MCP adds 39 tools for building ElevenAgents from any MCP client, covering workflow edits, attaching and detaching tools, test runs, agent generation, phone number import, batch calling, workspace secrets and ElevenAgents settings. Edits are staged in a draft, and only the publish tool makes them live. Connected clients ask for consent once more because of two new read scopes. See Hosted MCP.
All changes
ElevenAgents
- Model deprecations:
gpt-4.1,gpt-4.1-mini,gpt-4oandgpt-4o-miniare deprecated ahead of their shutdown on January 14, 2027. Requests fall back togpt-6-luna, for 10% of requests from December 15, 2026 and for all requests from January 9, 2027. The deprecatedgpt-5,gpt-5-miniandgpt-5-nanonow fall back togpt-6.1-sol,gpt-6.1-terraandgpt-6-lunainstead of the GPT-5.6 models announced on November 2. Thegemini-3.6-flashfallback togemini-3.8-flashreaches all requests on November 17, ahead of its retirement on November 19. Models past their provider shutdown dates, including Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 3 Haiku, Claude Sonnet 4, Gemini 2.0 Flash, Gemini 2.0 Flash-Lite,gpt-4-turboandgpt-3.5-turbo, resolve to their replacement models immediately, andgrok-betais removed from theLLMenum. See Models. - Fast tier for Gemini: Gemini agent models accept
service_tier: fastat priority rates, and a request is billed at the fast rate only when it is served at priority. Models that were already served at priority are billed at the standard rate until December 12. Custom guardrails addservice_tier(defaultstandard) and a matching picker in the dashboard; Gemini priority processing for guardrails stays free until December 4, after which only guardrails set tofastuse it and are charged for it.gpt-6-lunaagents without a reasoning effort setting now run atlowinstead ofmedium. The custom guardrail model picker no longer offers Gemini 2.5 Flash and Gemini 2.5 Flash Lite; existing guardrails and the API still accept them. - Knowledge base: Get chunking override and Update chunking override set
max_chunk_size,overlap_percentageandcustom_separatorsfor a document or folder, withnullinheriting from the parent folder, and the setting is available for every document and folder in the dashboard. Discover now on auto-discover crawl folders is available to every workspace. Folder responses returncrawl_job_idfor every crawl root folder. Voice agents read Markdown links in documents as their link text, and documents scraped from URLs keep ordered-list numbers without long runs of empty lines. The deprecateddependent_agentsfield in knowledge base list and search responses is always empty. See Knowledge base. - Conversation history: List conversations and message text search filter by tool ID with
tool_ids,tool_ids_successfulandtool_ids_errored, so tools that share a name are told apart, and by number withphone_number_idsandwhatsapp_phone_number_ids. Tool results in transcripts recordtool_id, and function-backed integration tool calls returnfunction_detailswith the parameters the LLM sent. Get conversation file lets server tools download a file the user attached during a live conversation, and thesystem__uploaded_file_idsdynamic variable passes the conversation’s attachment IDs to tool parameters. - Workflows and procedures: Workflow sub-agent nodes add
allow_interruptions_on_entry(defaultfalse) and an Allow interruptions switch, so callers can interrupt a node’s first response when it is set to generate immediately. Start procedure nodes are available to every workspace. Structured procedures add theupdate_statesystem tool, which sets dynamic variables, and procedure responses listwritten_dynamic_variables. Thetransfer_to_numbersystem tool acceptstransfer_rules, and workflow phone number nodes acceptprovider_configs, with one transfer configuration per telephony provider. Dead end analysis no longer flags nodes whose conditions cover every case. See Structured procedures. - Realtime API:
response.doneincludesusage, and tool call responses report the usage of the LLM call that made the tool call.conversation.item.createrejects malformed items, and every error for a rejected client event echoes itsevent_id. Realtime agents honortts.expressive_mode, and the Expressive mode switch is shown for them. The LLM usage calculator returns prices foreleven_realtime_v1_miniandeleven_realtime_v1_max. See Realtime models. - Branches: The Merge branch and Pull in changes dialogs resolve conflicts field by field for every workspace, replacing the read-only conflict list and the Force apply switch. Merges and rebases without
conflict_resolutionscompare voices, tools and tests entry by entry, as merge previews do. The Environment variables tab in Version Control is renamed Environments and opens on a view of how this agent’s variables differ by environment. - Privacy: Conversation history redaction adds the
criminal_recordentity type, redacts multi-paragraph call summaries and titles, and masks entities next to Korean particles and in Chinese and Japanese text without spaces. On PCI-compliant workspaces,PATCH /v1/convai/settingsrejects pre-call and post-call webhooks that are not on the allowlist with400pci_compliance_violation. See Conversation history redaction. - Channels and telephony: Voximplant calls can stream to an agent over a single WebSocket from a VoxEngine scenario; the integration is in limited availability and enabled per workspace. The WhatsApp integration adds a
whatsapp_send_imagetool that sends a JPEG or PNG image of up to 5 MB from a public URL, with an optional caption of up to 1,024 characters. In a Genesys Open Messaging handover, the agent tells the customer when a human agent joins. - Dashboard and analytics: Architect can ask clarifying questions with single- or multi-select options, close merge proposals and report who has access to an agent. Agent routes check only the permissions they use, so custom roles get the access they were granted, and viewers can no longer generate workflows or start batch calls. Tool failure alerts are tracked by tool ID and count code tool failures. Turn-taking latency is capped at the time since the agent finished speaking. Data collection discards string values outside the field’s
enum. Conversation billing starts when the WebSocket is accepted after setup. - Fixes: Interrupted turns no longer send stale retries to custom LLMs. A mid-turn fallback to another LLM no longer repeats the reply or runs words together. A structured procedure that ends a call after a sub-procedure step no longer fails with
Unsupported node type. A guardrail that fails on its final retry no longer leaves the blocked message in the transcript. Editing an auth connection takes effect on the next token request instead of after the cached token expires. Tool dependent agents include branches that use the tool only on workflow nodes.
Speech to Text
- Lower prices: Every Scribe model costs $0.20 per hour for batch transcription and $0.22 per hour for realtime transcription on self-serve and Business plans. Enterprise pricing is unchanged.
- Language detection in partials: With
include_language_detection=true, realtimepartial_transcriptmessages includelanguage_codeonce at least 4 words are detected with confidence on 2 consecutive partials.language_codeon committed transcripts with timestamps can benull. - Fixes: Realtime transcription no longer sends transcripts that contain only punctuation, such as
..., during silence, or a partial transcript after the committed transcript for the same segment. Committed transcripts with timestamps capitalize the first letter like text-only commits. Speech after a long continuous stream of about 36 seconds is no longer lost. Text frames that are not valid JSON returninput_errorand keep the session open instead of closing it withinternal_error.
Hosted MCP
- New tools: 39 tools cover agent draft edits, publishing, test runs and simulation tests, agent generation, phone number import, batch calling, workspace secrets, ElevenAgents settings, signed URLs and WhatsApp. Further tools read account usage, conversation audio, pronunciation dictionaries, workspace webhooks without their secrets, ElevenAgents concurrency limits and auto top-up state, and query conversations across every agent you can view. Agents can use Voice Library voices. See Hosted MCP.
- New scopes: MCP clients request the
user_readandpronunciation_dictionaries_readscopes, so each connected client asks for consent once more. - Voice listing:
creative_list_voicespages its results withpage_size(up to 100) andcursor/next_cursorinstead of returning only the first 25 voices. - Fixes: Tools no longer ask the client for a
contextargument describing the user’s goal. Validation errors returnisErrorwith the public tool name.
Workspaces
- Webhook testing and redelivery: Send test webhook event sends a signed sample event once and returns the endpoint’s status code and response time. Workspace admins can use Redeliver webhook delivery from a web session to send a stored delivery again with the same delivery ID and an
ElevenLabs-Webhook-Redelivery: trueheader; repeating it within 5 seconds returns409redelivery_in_flight. Test events and redeliveries share a limit of 10 per webhook per minute. - Agents environments permission: The
agents_environment_variables_writepermission, shown as Manage Agents environments in group settings, controls creating, updating and deleting agent environments and environment variables. Admins with Agents write access keep their access. - SCIM: Users can belong to several seat-type groups and receive the highest seat type among them. With SCIM routing on,
PATCHandPUTon a listed workspace group convert it to a routing group instead of returningGroup not found. - Audit logs: OAuth app authorizations, management and revocations are recorded, with three new
AuditActivityNamevalues.
Content provenance
- Watermark check:
POST /v1/content-provenance/watermark(beta) checks an uploaded audio file for an ElevenLabs watermark and returnsis_detectedanddetailswithproduct,model,generated_atandunique_id. Sendversionto choose the decoder; onlylatestis supported. It requires thewatermarkpermission and does not accept OAuth access tokens. See Content provenance.
Voices
- Voice design permission:
POST /v1/text-to-voice/design,POST /v1/text-to-voice,POST /v1/text-to-voice/create-previewsandPOST /v1/text-to-voice/{voice_id}/remixrequire thevoice_generationpermission on API keys, OAuth grants and workspace roles, and return401missing_permissionswithout it. - Voice Changer sharing: Voice Changer history items can be shared with workspace members from the share dialog.
- Fixes:
GET /v1/text-to-voice/{generated_voice_id}/streamreturns404voice_not_foundfor a preview that does not exist instead of500. Editing a Professional Voice Clone’s name, description or labels no longer retrains the voice.
Text to Speech
- Deprecated parameter:
apply_language_text_normalizationon the Text to Speech endpoints is deprecated. - WebSocket errors: The
stream-inputandmulti-stream-inputWebSockets close with1008model_not_foundfor an unknownmodel_idinstead of1011. - Fixes: Text edited on a v2 model is kept when switching back to a multi-speaker Eleven v3 or Eleven v4 dialogue.
Studio
- Pronunciation highlights: Audiobook projects highlight words matched by applied pronunciation rules, and a dialog breaks down conflicts when several rules match.
- Fixes: Duplicated or trimmed clips of a long video no longer freeze timeline playback. Video exports whose source decoder stalls, and exports of H.264 sources that switch parameter sets, fail with an error instead of hanging.
Image and video
- Flows preferences: Flows has preferences for default image, video, LLM and speech models for new nodes, video autoplay, connection visibility, notification sounds and snapping guides.
- Image editor: Editing sessions are saved to the server and resume after closing the tab or on another device, including while an AI operation runs. The Brand kits tab shows the active kit’s colors, typefaces, logos and references, which can be dragged onto the canvas, and the Layout panel switches between percent and pixel units.
Sound effects
- Delete takes: Each take on the History page has a delete button.
Billing
- Immediate cancellation:
GET /v1/user/subscriptionreturnscancels_immediately(boolean, defaultfalse). Self-serve plans whose renewal is waiting on 3-D Secure authentication now cancel right away and void the unpaid invoice instead of cancelling at the end of the period.
Reception.ai
- Reception API: Reception.ai partners can manage their customers’ workspaces in code with 75 endpoints under
/v1/reception. They can create a workspace for each customer, sell it one of their plans, follow billing, and set up the workspace’s business profile, receptionist (with rules, procedures and transfer rules), phone numbers, services, staff, locations, holidays, products, assets, knowledge sources and team. The endpoints are in the Python and JavaScript SDKs from v2.79.0 asreception. Requests need an API key created in the reseller admin panel; other API keys are rejected withnot_a_reseller_api_key. See Reception API and the quickstart.
SDK releases
JavaScript SDK
- v2.78.0 - Speech Engine streams keep the answer text from Gemini models instead of dropping it.
- v2.79.0 - Added a tool builder (
Tool,SchemaandHeader, exported from the package root) that defines webhook, client and system tools with chained calls and produces the request fortools.create()andtools.update(). See Tools as code. Added thereceptionclient for the Reception API.
Python SDK
- v2.78.0 - Speech Engine streams keep the answer text from Gemini models instead of dropping it.
- v2.79.0 - Added the tool builder in
elevenlabs.agent_tools, which defines webhook, client and system tools with chained calls and produces the request fortools.create()andtools.update(). See Tools as code.ConversationandAsyncConversationacceptcallback_unhandled_client_tool_call, called when the agent requests a client tool that has no registered handler. Added thereceptionclient for the Reception API.
ElevenLabs CLI
- v1.9.2 and v1.9.3 - Publishes the v1.9.1 changes to npm, Homebrew and Scoop, which the v1.9.1 release did not reach. The installed
sayskill uses a current default voice and notes that free plans can use premade voices but not Voice Library voices. - v1.10.0 -
onboardtreats a page that embeds the agent widget as wired, and ends a voice agent project with a link to talk to the agent and its dashboard page. - v1.11.0 - Agent, tool and test configs can be
.json,.yaml/.ymlor.tomlfiles, chosen by file extension.agents addandagents pulltake--config-formatto set the format of new files. - v1.12.0 - Updated the bundled API client.
- v1.12.1 -
tools diagramdraws one tool as a tree, in the terminal or as Mermaid, with each parameter’s value source, headers, auth connection and response handling. Workflow diagrams label tool nodes with names fromtools.json.agents pull --sparsekeeps existing minimal configs minimal instead of writing every default.
Packages
- @elevenlabs/client@1.36.0 - The volume set with
setVolumeapplies to WebRTC audio that starts playing after it was set. - @elevenlabs/client@1.36.1, @elevenlabs/react@1.22.1 and @elevenlabs/react-native@1.2.40 - WebRTC sessions that end because the LiveKit connection failed, for example with
SIGNAL_CLOSE,CONNECTION_TIMEOUT,MEDIA_FAILUREorAGENT_ERROR, now reachonDisconnectwithreason: "error"instead ofreason: "agent". Rooms the server closes on purpose are still reported asreason: "agent". - @elevenlabs/convai-widget-core@0.25.2 - The typing indicator stays visible after a tool call until the agent’s reply appears. Right-to-left replies, such as Arabic, lay out lists, blockquotes and table headers from the right, and the message and feedback inputs follow the direction of the typed text.
- @elevenlabs/convai-widget-core@0.26.0 and @elevenlabs/convai-widget-embed@0.26.0 - Added a
layout="page"attribute that makes the widget fill its host element as a full page that always shows the chat, with a call pane beside it on desktop. The widget no longer stays hidden when always expanded is turned on after it has loaded. - @elevenlabs/react@1.22.0, @elevenlabs/react-native@1.2.39 and @elevenlabs/convai-widget-embed@0.25.2 - Updated to the latest
@elevenlabs/clientand widget releases.
API changes
New endpoints
ElevenAgents
- Get conversation file -
GET /v1/convai/conversations/{conversation_id}/files/{file_id}downloads a file attached to a conversation. - Get chunking override -
GET /v1/convai/knowledge-base/{documentation_id}/chunking-override - Update chunking override -
PATCH /v1/convai/knowledge-base/{documentation_id}/chunking-overridewithchunking_override(max_chunk_size,overlap_percentageandcustom_separators, each a nullable integer or string array).
Workspaces
- Send test webhook event -
POST /v1/workspace/webhooks/{webhook_id}/test - Redeliver webhook delivery -
POST /v1/workspace/webhooks/{webhook_id}/deliveries/{delivery_id}/redeliver
Reception.ai
- Reception.ai - 75 endpoints under
/v1/receptionfor Reception.ai partners. Reseller-level groups areworkspaces,tiers,subscriptionsandbilling. Workspace-level groups, which take thexi-workspace-idheader, arebusiness_profile,receptionists(withrules,proceduresandtransfer_rules),phone_numbers,services,staff,locations,holidays,products(withstock),assets,knowledge_sourcesandteam(membersandinvites).
Content provenance
- Check watermark -
POST /v1/content-provenance/watermark(beta) accepts a multipartfileand optionalversion.
Updated endpoints
ElevenAgents
- List conversations
- Added optional
tool_ids,tool_ids_successful,tool_ids_errored,phone_number_idsandwhatsapp_phone_number_idsquery parameters (string arrays). Message text search (GET /v1/convai/conversations/messages/text-search) accepts the same five. - Added optional
data_collection_filteranddynamic_variable_filterquery parameters (string), single-value forms ofdata_collection_paramsanddynamic_variable_params.
- Added optional
- Get conversation details, test and simulation responses
- Tool results in transcripts add nullable
tool_id(string). - Integration webhook tool calls add nullable
function_details.
- Tool results in transcripts add nullable
- Create agent, Update agent and the agent get endpoints
TransferToNumberToolConfigaddstransfer_rules(array ofTransferRule, each with aconditionandprovider_configsfor Twilio, SIP trunk or Exotel).- Workflow phone number nodes add
provider_configs(array of Twilio, SIP trunk or Exotel transfers), mutually exclusive with a non-emptytransfer_destination. - Workflow sub-agent (
override_agent) nodes addallow_interruptions_on_entry(boolean, defaultfalse). CustomGuardrailConfigaddsservice_tier(LLMServiceTier, defaultstandard).ConfigEntityTypeaddscriminal_record.- Procedure references add
written_dynamic_variables(string array), also on List procedures. - The
LLMenum, also used by conversation overrides on the/v1/convai/conversationWebSocket, removesgrok-beta.
- Knowledge base document and summary responses add nullable
chunking_override.dependent_agentson summary responses is deprecated and always empty.
Text to Speech
- Text to Speech, Stream, With timestamps and Stream with timestamps -
apply_language_text_normalizationis deprecated.
Speech to Text
- Realtime WebSocket -
PartialTranscriptadds nullablelanguage_code(string).language_codeonCommittedTranscriptWithTimestampsand onSessionStarted.configis nullable.
Workspaces
- Service account API keys and workspace groups -
PermissionTypeandWorkspaceGroupPermissionaddagents_environment_variables_writeandwatermark.
Billing
- Get subscription - Added
cancels_immediately(boolean, defaultfalse).